INDEX

Explanations

occurrences of the word "of."

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

.LayoutStyle

-0.17

priv

-0.15

IVO

-0.15

ombat

-0.15

olec

-0.14

ibr

-0.14

anzi

-0.14

ãĤ£

-0.14

Ð²Ð¸Ð¶

-0.14

era

-0.13

POSITIVE LOGITS

iffer

0.15

dock

0.15

 Strand

0.15

 Canter

0.15

poster

0.14

Poster

0.14

 Duty

0.13

Kaf

0.13

ipel

0.13

ceipt

0.13

Activations Density 0.104%

occurrences of the word "of."

No Comments

No Known Activations